AI will shape the energy transition

Artificial intelligence will have a wide-reaching impact on the entire energy sector and determine the speed and direction of the transition, according to Hypergiant founder and CEO Ben Lamm

Ben Lamm is the CEO and founder of US-based advanced technology solutions provider Hypergiant. The Texan serial entrepreneur—it is his fifth company—embarked on his most ambitious enterprise to-date when he co-founded Hypergiant in 2018.

Hypergiant is focused on advanced artificial intelligence (AI) for clients in a wide range of range of sectors from oil drilling and fluid dynamics to entertainment and healthcare. It has an impressive roster of industry partners: consultancies Booz Allen Hamilton and EY; applied science company Dynetics; software companies Adobe, Microsoft, AWS and SAP; and computer hardware company Nvidia.

Likewise, its clients include leaders in diverse areas of the oil and gas sector including Shell, US E&P independent Marathon Oil, oilfield services company Schlumberger, conglomerate GE and marketing and trading firm Pacific Summit Energy.

How can AI aid the decarbonisation of oil and gas production?

Lamm: For decades, oil and gas producers have faced pressure to improve their carbon footprint. Technology in general has proven to be one of the most effective levers for them to pull, with AI in particular now surfacing as the newest and hottest lever of them all. Given that the production phase of the industry is responsible for less than 15pc of the emissions released, the bulk of the problem lies downstream of the producer functions which include exploration, drilling, and processing/refining. However, for these four discrete categories, the following examples demonstrate how AI is becoming one of the more widely accepted approaches for addressing decarbonisation.

“The result [of AI] is the more efficient distribution of power at lower cost and risk to both providers and consumers. Literally everyone wins”

In exploration, improvements in finding the oil or gas can be made through the application of AI methods so that the geothermal intelligence and other exploration data can be used to much more effectively predict where additional reserves are located.  

In the case of production, methane leakage can be detected and reduced and/or eliminated with both the use of optical gas imaging cameras at the valves/fittings and drone-mounted leak detection sensors throughout the sites. Additionally, routine methane flaring can be dramatically reduced via more effective production forecasting due to more accurate machine-learning infused data. Lastly, the analysis and application of predictive weather models help achieve greatly enhanced disaster response.

The processing/refining phase is definitely one of most carbon-intensive parts of the process and the area in which detection devices continue to get smarter and smarter. Carbon leaks can be detected, predicted, and ultimately reduced/eliminated via drone-mounted leak detection sensors and fence-line scanners.

Once detected, the data can be analysed automatically with AI resulting in predictive maintenance plans so that leaks are less likely to happen. The faster these planned and unplanned leaks can be identified and then acted upon is reliant upon smarter and more real-time data—and that is where AI is highly impactful.

Energy systems are becoming more distributed and including more sources of power. How can AI improve the performance of smart grids?

Lamm: This is an important question because it affects us all, from our homes and into our businesses, which in many cases right now are one and the same. Due to the number of variables to consider and challenges associated with upgrading and evolving an entrenched, legacy system of power distribution, AI must be leveraged in order to do so most efficiently, effectively and responsibly.

“There is simply no way to achieve these types of results with traditional technologies or humans alone”

The truth is, AI can help improve the performance of smart grids in the same way it can improve the conditions within any other use case where it can be applied. By consuming and processing vast amounts of data and accounting for fluctuating variables and scenarios, intelligent technologies identify patterns and produce insights that help humans make better decisions towards achieving a desired goal.

In the case of power distribution, AI will help providers safely deliver clean and reliable power to consumers from dynamic sources while giving those consumers tools to more effectively manage their own power consumption. What was once a fragmented patchwork of disjointed systems fraught with uncertainty and risk will become a more efficient and robust ecosystem infinitely more capable of managing and responding to the challenges of our modern world.